File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)
Supplementary

Article: Geometric Knowledge Embedding for unsupervised domain adaptation

TitleGeometric Knowledge Embedding for unsupervised domain adaptation
Authors
KeywordsDomain adaptation
Graph-based model
Geometric knowledge
Graph convolutional network
Maximum Mean Discrepancy
Issue Date2020
PublisherElsevier BV. The Journal's web site is located at http://www.elsevier.com/locate/knosys
Citation
Knowledge-Based Systems, 2020, v. 191, p. article no. 105155 How to Cite?
AbstractDomain adaptation aims to transfer auxiliary knowledge from a source domain to enhance the learning performance on a target domain. Recent studies have suggested that deep networks are able to achieve promising results for domain adaptation problems. However, deep neural networks cannot reveal the underlying geometric information from input data. Indeed, such geometric information is very useful for describing the relationship between the samples from source and target domains. In this paper, we propose a novel learning algorithm named GKE, which stands for Geometric Knowledge Embedding. In GKE, we use a graph-based model to explore the underlying geometric structure of the input source and target data based on their similarities. Concretely, we develop a graph convolutional network to learn discriminative representations based on the constructed graph. To obtain effective transferable representations, we match source and target domains by reducing the Maximum Mean Discrepancy (MMD) between their learned representations. Extensive experiments on real-world data sets demonstrate that the proposed method outperforms existing domain adaption methods.
Persistent Identifierhttp://hdl.handle.net/10722/287957
ISSN
2019 Impact Factor: 5.921
2015 SCImago Journal Rankings: 2.140

 

DC FieldValueLanguage
dc.contributor.authorWu, H-
dc.contributor.authorYan, Y-
dc.contributor.authorYe, Y-
dc.contributor.authorNg, MK-
dc.contributor.authorWu, Q-
dc.date.accessioned2020-10-05T12:05:44Z-
dc.date.available2020-10-05T12:05:44Z-
dc.date.issued2020-
dc.identifier.citationKnowledge-Based Systems, 2020, v. 191, p. article no. 105155-
dc.identifier.issn0950-7051-
dc.identifier.urihttp://hdl.handle.net/10722/287957-
dc.description.abstractDomain adaptation aims to transfer auxiliary knowledge from a source domain to enhance the learning performance on a target domain. Recent studies have suggested that deep networks are able to achieve promising results for domain adaptation problems. However, deep neural networks cannot reveal the underlying geometric information from input data. Indeed, such geometric information is very useful for describing the relationship between the samples from source and target domains. In this paper, we propose a novel learning algorithm named GKE, which stands for Geometric Knowledge Embedding. In GKE, we use a graph-based model to explore the underlying geometric structure of the input source and target data based on their similarities. Concretely, we develop a graph convolutional network to learn discriminative representations based on the constructed graph. To obtain effective transferable representations, we match source and target domains by reducing the Maximum Mean Discrepancy (MMD) between their learned representations. Extensive experiments on real-world data sets demonstrate that the proposed method outperforms existing domain adaption methods.-
dc.languageeng-
dc.publisherElsevier BV. The Journal's web site is located at http://www.elsevier.com/locate/knosys-
dc.relation.ispartofKnowledge-Based Systems-
dc.subjectDomain adaptation-
dc.subjectGraph-based model-
dc.subjectGeometric knowledge-
dc.subjectGraph convolutional network-
dc.subjectMaximum Mean Discrepancy-
dc.titleGeometric Knowledge Embedding for unsupervised domain adaptation-
dc.typeArticle-
dc.identifier.emailNg, MK: michael.ng@hku.hk-
dc.identifier.authorityNg, MK=rp02578-
dc.description.naturelink_to_subscribed_fulltext-
dc.identifier.doi10.1016/j.knosys.2019.105155-
dc.identifier.scopuseid_2-s2.0-85075460455-
dc.identifier.scopuseid_2-s2.0-85075460455-
dc.identifier.hkuros315734-
dc.identifier.volume191-
dc.identifier.spagearticle no. 105155-
dc.identifier.epagearticle no. 105155-
dc.publisher.placeNetherlands-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats